© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 90686
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on decimal number tokens (floating‐point values like “0.265625,” “1.9697265625,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .ColumnHeadersHeightSizeMode
    -0.06
    	script
    -0.06
    سم
    -0.06
     plaats
    -0.06
     представляет
    -0.06
    (test
    -0.06
    .indent
    -0.06
    ablytyped
    -0.06
     graz
    -0.06
    xDE
    -0.06
    POSITIVE LOGITS
    StringUtils
    0.07
     Shell
    0.07
     Karlov
    0.07
     []↵
    0.06
     Bre
    0.06
    ительной
    0.06
     Mov
    0.06
    _episode
    0.06
     Spears
    0.06
     AD
    0.06
    Activations Density 0.082%

    No Known Activations